Ohno Y, Aoki K, Aoki N
Int J Epidemiol. 1979 Sep;8(3):273-80. doi: 10.1093/ije/8.3.273.
The geographic pattern of disease has been visually studied by depicting the categorized mortality or morbidity rates on a map. Visual study, however, by no means indicates the statistical significance of observed clusters, i.e., whether or not the geographic aggregations could occur by chance alone. In this paper, an approach for assessing the deviation from chance expectation of the geographic pattern actually observed on the map is described. A simple chi-square test is proposed, and its validity is substantiated by a Monte Carlo approach, which is derived analytically as a special case of Knox's test for space--time clustering. The parameters required for the test are (1) total number of areas, (2) numbers of subareas for each mortality of morbidity category, (3) total number of geographically adjacent areas, and (4) observed numbers of adjacent areas having concordant category pairs.
通过在地图上描绘分类后的死亡率或发病率，对疾病的地理分布模式进行了直观研究。然而，直观研究绝不能表明所观察到的聚集的统计学显著性，即地理聚集是否仅由偶然因素导致。本文描述了一种评估地图上实际观察到的地理模式与偶然预期偏差的方法。提出了一种简单的卡方检验，并通过蒙特卡罗方法证实了其有效性，该方法作为诺克斯时空聚集检验的一个特殊情况通过解析推导得出。该检验所需的参数为：（1）区域总数；（2）每个发病率或死亡率类别的子区域数量；（3）地理上相邻区域的总数；（4）具有一致类别对的相邻区域的观察数量。
